Video Analytics Evaluation

2. The method of claim 1, wherein displaying the image from the particular time in the recorded video comprises generating a graphical user interface for presentation on a display of a computing device.

3. The method of claim 1, wherein displaying the indication whether the second video analysis evaluation on the recorded video satisfies the similarity criterion with the first video analysis evaluation on the recorded video comprises displaying a depiction of a virtual line crossing.

4. The method of claim 1, wherein displaying the indication whether the second video analysis evaluation on the recorded video satisfies the similarity criterion with the first video analysis evaluation on the recorded video comprises displaying a depiction of a bounding box.

5. The method of claim 4, wherein the bounding box is positioned around a region of the image where the evaluation of the event or the ground truth determination detected an object.

6. The method of claim 4, wherein the bounding box is positioned around a region of the image where the evaluation of the event or the ground truth determination detected motion.

7. The method of claim 1, wherein displaying the indication whether the second video analysis evaluation on the recorded video satisfies the similarity criterion with the first video analysis evaluation on the recorded video comprises displaying a depiction of boundaries around a portion of the image that corresponds to an area of interest.

8. The method of claim 7, wherein the area of interest comprises an area of a property that is monitored by the camera that captured the recorded video.

9. The method of claim 1, wherein displaying the indication whether the second video analysis evaluation on the recorded video satisfies the similarity criterion with the first video analysis evaluation on the recorded video comprises displaying text indicating that the event of interest does not match the ground truth determination for the recorded video.

10. The method of claim 1, wherein the indication whether the second video analysis evaluation on the recorded video satisfies the similarity criterion with the first video analysis evaluation on the recorded video includes a user-selectable icon.

12. The method of claim 1, wherein identifying the particular time in the recorded video when the analysis determination event of interest does not match the ground truth determination for the recorded video using the data indicative of whether any of the plurality of events of interest were detected in the respective recorded video comprises identifying the particular time in the recorded video when one or more of a false positive motion detection event, a false negative motion detection event, a false positive object detection event, a false negative object detection event, or a false object classification event occurred.

13. The method of claim 1, wherein identifying the particular time in the recorded video when the event of interest does not match the ground truth determination for the recorded video using the data indicative of whether any of the plurality of events of interest were detected in the respective recorded video comprises identifying the particular time in the recorded video when a motion detection latency occurred.

14. The method of claim 13, wherein the motion detection latency comprises motion detection at a time in the recorded video that is greater than a threshold time duration after ground truth motion detection.

15. The method of claim 1, wherein identifying the particular time in the recorded video when the event of interest does not match the ground truth determination for the recorded video using the data indicative of whether any of the plurality of events of interest were detected in the respective recorded video comprises identifying the particular time in the recorded video when an object detection latency occurred.

16. The method of claim 15, wherein the object detection latency comprises object detection at a time in the recorded video that is greater than a threshold time duration after ground truth object detection.

17. The method of claim 1, wherein identifying the recorded video for the evaluation of the event comprises selecting a video clip from a database of stored video clips.